Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-Agent Path Finding on 3-agent 5x5 (evaluation set)
Loading...
62.67
Valid Rate
Qwen3-4B + GRPO + Ours
16.2132
28.2741
40.335
52.3959
Jun 16, 2026
Valid Rate
Optimal Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Valid Rate
Optimal Rate
Qwen3-4B + GRPO + Ours
Backbone=Qwen3-4B, Tra...
2026.06
62.67
35.33
Kimi-K2.5
2026.06
57.33
34
Qwen3-4B + GRPO (random)
Backbone=Qwen3-4B, Tra...
2026.06
50.67
29.33
GPT-5.4
2026.06
42.67
31.33
Gemini-3.1-Pro
2026.06
35.33
20
Grok-4.2
2026.06
29.33
18.67
Qwen3-4B (base)
Backbone=Qwen3-4B
2026.06
18
16.67
Feedback
Search any
task
Search any
task